calibre/recipes/respekt.recipe
2012-11-18 23:53:33 +05:30

38 lines
1.3 KiB
Plaintext

# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import unicode_literals
from calibre.web.feeds.recipes import BasicNewsRecipe
import re
class respektRecipe(BasicNewsRecipe):
__author__ = 'bubak'
title = u'Respekt'
publisher = u'Respekt'
description = 'Respekt'
oldest_article = 1
max_articles_per_feed = 20
feeds = [
(u'Všechny články', u'http://respekt.ihned.cz/index.php?p=R00000_rss')
,(u'Blogy', u'http://blog.respekt.ihned.cz/?p=Rb00VR_rss')
#,(u'Respekt DJ', u'http://respekt.ihned.cz/index.php?p=R00RDJ_rss')
]
encoding = 'cp1250'
language = 'cs'
cover_url = 'http://respekt.ihned.cz/img/R/respekt_logo.png'
remove_javascript = True
no_stylesheets = True
remove_tags = [dict(name='div', attrs={'class':['d-tools', 'actions']})]
remove_tags_before = dict(name='div',attrs={'id':['detail']})
remove_tags_after = dict(name='div',attrs={'class':'d-tools'})
preprocess_regexps = [(re.compile(r'<div class="paid-zone".*', re.DOTALL|re.IGNORECASE), lambda match: 'Za zbytek článku je nutno platit. </body>'),
(re.compile(r'.*<div class="mm-ow">', re.DOTALL|re.IGNORECASE), lambda match: '<body>'),
(re.compile(r'<div class="col3">.*', re.DOTALL|re.IGNORECASE), lambda match: '</body>')]
keep_only_tags = []